With FlowiseAI, you can create and run LLM apps without writing any code, using predefined templates or customizing your own. You can also integrate FlowiseAI with various data sources, APIs, and cloud services to enhance your LLM apps.
In this article, we will show you how to install and setup FlowiseAI in Ubuntu, using two different methods: Node.js and Docker. We will also show you how to configure and use FlowiseAI to create and run LLM apps.
Before you install and setup FlowiseAI in Ubuntu, you need to make sure that your system meets the following hardware and software requirements:
- A computer with at least 4GB of RAM and 10GB of disk space.
- An internet connection.
- Ubuntu 18.04 LTS or later.
- NodeJS 18.15.0 or later.
To install NodeJS in Ubuntu, you can use the following commands:
sudo apt update sudo apt install curl curl -sL https://deb.nodesource.com/setup_18.x | sudo bash - sudo apt install nodejs
You can verify that NodeJS is installed by running:
You should see something like:
There are two ways to install FlowiseAI in Ubuntu: using npm or using Docker.
npm is a package manager for NodeJS that allows you to install and manage modules and dependencies. To install FlowiseAI using npm, you can use the following command:
npm install -g flowise
This will install FlowiseAI globally on your system, so you can access it from any directory.
Once the installation is complete, you can start FlowiseAI using the below command:
npx flowise start
Using Docker Compose
Docker is a tool that allows you to create and run containers, which are isolated environments that contain everything you need to run an application. To install FlowiseAI using Docker, you need to have Docker and Docker compose installed on your system. You can follow the instructions here to install Docker and Docker Compose on Ubuntu.
Once you have Docker installed, you can pull the FlowiseAI repository from the official Github.
git clone https://github.com/FlowiseAI/Flowise.git
Navigate into the docker directory and copy the
cd FlowiseAI/docker cp .env.example .env
Now you can change the variables inside the
.env file as per your need. Once you are ready you can deploy FlowiseAI using Docker compose
docker-compose up -d
Once the deployment is completed, FlowiseAI will be running on port 3000.
Before you use FlowiseAI, you may want to configure some settings to customize your experience. There are two main settings that you can configure: authentication and environment variables.
Setting up authentication
By default, FlowiseAI does not require any authentication to access its web interface. However, if you want to add some security to your instance, you can enable app-level authentication by adding
FLOWISE_PASSWORD to the
.env file in the
packages/server folder. For Docker compose deployment the .env file is located in
docker directory. For example:
Configuring these variables will prompt you to enter the username and password when you access FlowiseAI from your browser.
Setting up environment variables
FlowiseAI supports different environment variables to configure your instance. You can specify the following variables in the
.env file inside the packages/server folder:
PORT: The port number that FlowiseAI will listen on. Default is 3000.
FLOWISE_USERNAME: The username for app-level authentication. Default is none.
FLOWISE_PASSWORD: The password for app-level authentication. Default is none.
FLOWISE_LOG_LEVEL: The level of logging that FlowiseAI will output. Possible values are: error, warn, info, verbose, debug, silly. Default is info.
FLOWISE_LOG_FILE: The path of the file that FlowiseAI will write logs to. Default is none.
FLOWISE_LOG_ROTATE: The frequency of log rotation. Possible values are: daily, weekly, monthly. Default is none.
After starting and configuring FlowiseAI, you can use it to create and run LLM apps from your browser. To access the web interface of FlowiseAI, you need to open the following URL in your browser:
Where PORT is the port number that FlowiseAI is listening on. For example, if you started FlowiseAI on port 3000, you need to open:
You should see something like this:
Creating and running LLM flows
To create an LLM flow, you need to click on the “Create New” button on the top right corner of the web interface. This will open a dialog where you can choose a template or a blank flow. A template is a predefined flow that performs a specific task, such as sentiment analysis, text summarization, or question answering. A blank flow is an empty flow that you can customize with your own components.
After choosing a template or a blank flow, you will be taken to the flow editor, where you can see and edit your flow. A flow consists of nodes and links. A node is a component that performs a specific function, such as input, output, processing, or integration. A link is a connection between two nodes that transfers data from one node to another.
To edit a node, you need to double-click on it. This will open a dialog where you can see and change its properties, such as name, description, parameters, and outputs. To delete a node, you need to right-click on it and select “Delete”. To add a new node, you need to drag and drop it from the left panel to the canvas.
To create a link between two nodes, you need to drag and drop from the output port of one node to the input port of another node. To delete a link, you need to right-click on it and select “Delete”. To edit a link, you need to double-click on it. This will open a dialog where you can see and change its properties, such as name and description.
To run a flow, you need to click on the “Run” button on the top right corner of the flow editor. This will execute your flow and show you the results in the output nodes. You can also see the logs of your flow in the bottom panel.
Here is an example of an LLM flow that performs sentiment analysis on user input:
In this article, we have shown you how to install and setup FlowiseAI in Ubuntu using two different methods: npm and Docker. We have also shown you how to configure and use FlowiseAI to create and run LLM apps from your browser.